Vehicle lamp projection method, projection area calibration method, product and vehicle

Abstract

The invention provides a vehicle lamp projection method, a projection area calibration method, a product and a vehicle, and belongs to the technical field of projection. The vehicle lamp projection method comprises the steps that when a plurality of vehicle lamps jointly project, distortion correction is carried out on a to-be-projected image according to a projection area of the plurality of vehicle lamps, and the projection area is a target rectangular area in a combined projection area of the plurality of vehicle lamps; and according to the to-be-projected images after distortion correction, respectively determining target to-be-projected images during respective projection of the plurality of vehicle lamps. The projection effect of the automobile lamp is improved.

Description

Technical Field

[0001] The embodiments of the present application relate to the technical field of projection, and specifically, to a vehicle light projection method, a projection area calibration method, a product, and a vehicle. Background Art

[0002] The rapid development of science and technology is constantly driving changes in the automotive industry. Smart headlights are a product of this wave of change. Compared with traditional vehicle headlights, smart headlights can automatically adjust the lighting range, intensity and direction according to different road conditions and driving scenarios, greatly improving nighttime driving safety and reducing traffic accidents caused by insufficient lighting. They are of great significance in protecting the lives and property of many drivers and passengers. However, in the current dual-lamp fusion technology, when multiple headlights are projected together, the final projected image will be distorted, resulting in poor image projection effect. Summary of the Invention

[0003] The embodiments of the present application provide a vehicle light projection method, a projection area calibration method, a product, and a vehicle, aiming to improve the projection effect of vehicle lights.

[0004] In a first aspect, an embodiment of the present application provides a vehicle light projection method, the method comprising: When multiple headlights are projected together, distortion correction is performed on the projected image according to the projection areas of the multiple headlights, where the projection area is the target rectangular area within the joint projection area of ​​the multiple headlights; According to the distortion-corrected image to be projected, target images to be projected when each of the plurality of vehicle lights is projected are determined respectively.

[0005] Optionally, the target rectangle includes a maximum inscribed rectangle.

[0006] Optionally, performing distortion correction on the projected image according to the projection areas of the multiple headlights includes: The image to be projected is scaled according to the size of the target rectangular area to obtain the distortion-corrected image to be projected.

[0007] Optionally, determining target images to be projected when each of the plurality of headlights is projected according to the distortion-corrected images to be projected includes: executing a gradient fusion strategy according to the overlapping projection areas of the plurality of headlights and the distortion-corrected image to be projected, and determining gradient images of the plurality of headlights respectively; According to the respective gradient images of the plurality of headlights, target images to be projected by the respective headlights are determined.

[0008] Optionally, the method further includes: An AND operation is performed on the binary mask images corresponding to the maximum projection areas of the plurality of headlights to determine an overlapping area of ​​the projections of the plurality of headlights.

[0009] Optionally, executing a gradient fusion strategy based on the overlapping projection areas of the plurality of headlights and the distortion-corrected image to be projected to respectively determine the gradient images of the plurality of headlights includes: Determining coefficient matrices of overlapping images corresponding to the plurality of headlights, respectively, based on the projection overlap areas of the plurality of headlights and the distortion-corrected image to be projected; The gradient images of the plurality of headlights are determined according to the coefficient matrices of the distortion-corrected image to be projected and the overlapping images corresponding to the plurality of headlights.

[0010] Optionally, the method further includes: An AND operation is performed on the binary mask image corresponding to the overlapping area of ​​the projections of the multiple headlights and the image to be projected after the distortion correction to determine the overlapping images corresponding to the multiple headlights.

[0011] Optionally, respectively determining coefficient matrices of overlapping images corresponding to the plurality of vehicle lights includes: For the overlapping images of each headlight, the linear coefficient after gamma correction corresponding to each pixel point is determined row by row to obtain a coefficient matrix of the overlapping image corresponding to the headlight.

[0012] Optionally, the multiple headlights include a left headlight and a right headlight. For overlapping images of each headlight, a linear coefficient corresponding to each pixel after gamma correction is determined row by row to obtain a coefficient matrix of the overlapping image corresponding to the headlight, including: For each row of pixels in the overlapping image of the left headlight, determining first linear coefficients corresponding to the pixels in descending order from left to right, and performing gamma correction on the first linear coefficients to determine a first coefficient matrix for the overlapping image of the left headlight; For the overlapping image of the right headlight, the second linear coefficient of each pixel point in the overlapping image of the left headlight is determined based on the first linear coefficient corresponding to each pixel point in the overlapping image of the right headlight, and the second linear coefficient is gamma corrected to determine the second coefficient matrix of the overlapping image of the right headlight.

[0013] Optionally, determining target images to be projected by each of the plurality of headlights according to the respective gradient images of the plurality of headlights includes: According to the homography matrices and the maximum projection image corresponding to the multiple headlights, perspective transformation is performed on the gradient images corresponding to the multiple headlights to determine target images to be projected by the multiple headlights.

[0014] In a second aspect, an embodiment of the present application provides a method for calibrating a vehicle lamp projection area, the method comprising: When projections of multiple headlights overlap, determining a joint projection area of ​​the multiple headlights; A target rectangular area is determined in the joint projection area of ​​the multiple headlights as the projection area when the multiple headlights are jointly projected.

[0015] Optionally, the target rectangle includes a maximum inscribed rectangle.

[0016] Optionally, determining the target rectangular area in the joint projection area of ​​the plurality of vehicle lights includes: In the joint projection area of ​​the multiple vehicle lights, the area of ​​the maximum inscribed rectangle is determined by a maximum rectangle algorithm.

[0017] Optionally, determining the joint projection area of ​​the plurality of vehicle lights includes: The joint projection area of ​​the multiple headlights is determined according to the binary mask images corresponding to the maximum projection areas of the respective headlights.

[0018] Optionally, determining the joint projection area of ​​the plurality of headlights according to the binary mask images corresponding to the respective maximum projection areas of the plurality of headlights includes: An OR operation is performed on the binary mask images corresponding to the respective maximum projection areas of the plurality of headlights to determine a joint projection area of ​​the plurality of headlights.

[0019] Optionally, the method further includes: According to the homography matrices of the plurality of headlights, binary mask images corresponding to the maximum projection areas of the plurality of headlights are determined.

[0020] Optionally, the method further includes: For each headlight, determining the projection coordinates of each feature point in the feature calibration image based on the projection of the headlight on the feature calibration image; The homography matrix corresponding to the vehicle light is calculated according to the projection coordinates of each feature point and the pixel coordinates of each feature point in the feature calibration image.

[0021] Optionally, the feature calibration image includes a plurality of feature points, and the number of the plurality of feature points is greater than a preset number.

[0022] Optionally, determining, according to the homography matrices of the plurality of headlights, the binary mask images corresponding to the maximum projection areas of the plurality of headlights includes: determining the maximum projection areas of the plurality of headlights according to the maximum projection images of the plurality of headlights and the homography matrices of the plurality of headlights; Determining a minimum circumscribed rectangle corresponding to the maximum projection area of ​​each of the plurality of headlights; According to the size of the minimum circumscribed rectangle and the maximum projection area of ​​each of the plurality of headlights, a binary mask image corresponding to the maximum projection area of ​​each of the plurality of headlights is determined respectively.

[0023] Optionally, determining the maximum projection areas of the plurality of headlights according to the maximum projection images of the plurality of headlights and the homography matrices of the plurality of headlights includes: For each headlight, the projection coordinates of each corner point of the maximum projection area corresponding to the headlight are calculated based on the pixel coordinates of each corner point of the maximum projection image corresponding to the headlight and the homography matrix of the headlight to determine the maximum projection area of ​​the headlight.

[0024] Optionally, determining the minimum circumscribed rectangle corresponding to the maximum projection area of ​​each of the plurality of headlights includes: Determine, according to the projection coordinates of the corner points of the maximum projection areas of the plurality of headlights, four corner points corresponding to the maximum projection abscissa, the minimum projection abscissa, the maximum projection ordinate, and the minimum projection ordinate; Determine, based on the four corner points, a minimum circumscribed rectangle corresponding to the maximum projection area of ​​each of the plurality of headlights.

[0025] In a third aspect, an embodiment of the present application provides a projection control system, the system comprising a plurality of vehicle lights and a control module, the control module being used to execute the vehicle light projection method described in the first aspect of the embodiment, or to execute the vehicle light projection area calibration method described in the second aspect of the embodiment.

[0026] In a fourth aspect, an embodiment of the present application provides an electronic device, comprising: at least one processor, and a memory, wherein the memory stores a computer program that can be run on the processor, wherein when the processor executes the computer program, it executes the vehicle light projection method described in the first aspect of the embodiment, or executes the vehicle light projection area calibration method described in the second aspect of the embodiment.

[0027] In a fifth aspect, an embodiment of the present application provides a non-volatile readable storage medium, wherein the non-volatile readable storage medium stores a computer program, wherein when the computer program is executed by a processor, the vehicle light projection method described in the first aspect of the embodiment is executed, or the vehicle light projection area calibration method described in the second aspect of the embodiment is executed.

[0028] In a sixth aspect, an embodiment of the present application provides a computer program product, comprising a computer program / instruction, which, when executed by a processor, implements the vehicle light projection method described in the first aspect of the embodiment, or executes the vehicle light projection area calibration method described in the second aspect of the embodiment.

[0029] In a seventh aspect, an embodiment of the present application provides a vehicle, which is used to execute the vehicle light projection method described in the first aspect of the embodiment, or execute the vehicle light projection area calibration method described in the second aspect of the embodiment, or includes a projection control system as described in the third aspect of the embodiment.

[0030] Beneficial effects: In the vehicle light projection method provided in this embodiment, when multiple vehicle lights are projecting together, distortion correction is performed on the image to be projected based on the projection areas of the multiple vehicle lights, where the projection area is the target rectangular area in the joint projection area of ​​the multiple vehicle lights. Based on the image to be projected after distortion correction, the target images to be projected when the multiple vehicle lights are projecting individually are determined.

[0031] By using the target rectangular area in the joint projection area of ​​multiple headlights as the projection area when multiple headlights are projecting together, distortion correction is performed on the projected image, so that the target images to be projected when multiple headlights are projecting individually are finally projected into the rectangular area. The correction optimizes the shape of the projection area, avoids the problem of distortion of the final projection image when multiple headlights are projecting together, and improves the projection effect of the headlights. BRIEF DESCRIPTION OF THE DRAWINGS

[0032] In order to more clearly illustrate the technical solutions of the embodiments of the present application, the following briefly introduces the drawings required for use in the description of the embodiments of the present application. Obviously, the drawings described below are only some embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without any creative work.

[0033] Figure 1 This is a flowchart of the steps of the vehicle headlight projection area calibration method proposed in one embodiment of the present application; Figure 2 Schematic diagram of a binary mask image of a minimum bounding rectangle proposed in one embodiment of the present application; Figure 3 1 is a schematic diagram of a binary mask image corresponding to the maximum projection area of ​​each headlight provided in an embodiment of the present application; Figure 4 is a schematic diagram of a binary mask map of a joint projection area proposed in one embodiment of the present application; Figure 5 is a schematic diagram of a binary mask image of a maximum inscribed rectangle proposed in one embodiment of the present application; Figure 6 This is a flowchart of the steps of the vehicle light projection method provided by one embodiment of the present application; Figure 7 is a schematic diagram of an image to be projected after distortion correction proposed in one embodiment of the present application; Figure 8 is a visual schematic diagram of the gradient images of each headlight proposed in an embodiment of the present application; Figure 9 is a schematic diagram of target images to be projected for each headlight provided in one embodiment of the present application; Figure 10 This is a schematic diagram of the structure of a projection control system proposed in one embodiment of the present application; Figure 11 is a schematic diagram of an electronic device proposed in one embodiment of the present application; Figure 12 is a schematic diagram of a non-volatile readable storage medium provided in one embodiment of the present application; Figure 13 It is a schematic diagram of a computer program product proposed in one embodiment of the present application. DETAILED DESCRIPTION

[0034] The following will be combined with the drawings in the embodiments of this application to clearly and completely describe the technical solutions in the embodiments of this application. Obviously, the embodiments described are part of the embodiments of this application, not all of them. Based on the embodiments in this application, all other embodiments obtained by ordinary technicians in this field without making creative efforts are within the scope of protection of this application.

[0035] The rapid development of science and technology is constantly driving changes in the automotive industry. Smart headlights are a product of this wave of change. Compared with traditional vehicle headlights, smart headlights can automatically adjust the lighting range, intensity and direction according to different road conditions and driving scenarios, greatly improving nighttime driving safety and reducing traffic accidents caused by insufficient lighting. They are of great significance in protecting the lives and property of many drivers and passengers. However, in the current dual-lamp fusion technology, when the two headlights are projected together, the final projected image will be distorted and have inconsistent brightness, resulting in poor projection effects.

[0036] Therefore, the embodiments of the present application provide a vehicle light projection method and a vehicle light projection area calibration method, which can optimize the shape of the projection area when multiple vehicle lights are projected together, thereby reducing the distortion problem of the projected image.

[0037] Reference Figure 1 , shows a flowchart of the steps of a method for calibrating a vehicle lamp projection area provided by an embodiment of the present application. The method for calibrating a vehicle lamp projection area may include the following steps: S101: When projections of multiple headlights overlap, determining a joint projection area of ​​the multiple headlights.

[0038] Specifically, the multiple headlights can be DLP (Digital Light Processing) headlights, which can project images on the ground to provide better visual effects. The multiple headlights can include left and right headlights on the front of the vehicle. In the actual implementation process, the number of headlights in the multiple headlights can also be set according to the needs of actual applications, and this year's embodiment does not impose any restrictions.

[0039] When multiple headlights are projected together, in order to avoid distortion of the final projected image, this method determines the target rectangular area in the joint projection area of ​​multiple headlights as the projection area of ​​the joint projection of multiple headlights, optimizes the shape of the projection area, and makes the final projection image more square and the projection effect better.

[0040] When multiple headlights jointly project an image, in order to achieve a better display effect of the image on the projection plane, the projection area when two headlights jointly project can be calibrated in advance. For example, the projection area of ​​the vehicle can be calibrated when the vehicle leaves the factory, and then in each subsequent projection, the multiple headlights can be controlled based on the calibrated projection area to display the image to be projected in the projection area of ​​the projection plane.

[0041] In a feasible implementation manner, determining the joint projection area of ​​the multiple vehicle lights may include the following steps: A1: Determine the homography matrix of each of the plurality of vehicle lights.

[0042] Specifically, in the calibration process of the projection area of ​​the headlights, it is first necessary to determine the homography matrix corresponding to each headlight. The homography matrix is ​​a matrix that describes the mapping relationship between points on two planes and describes the geometric transformation relationship of the image at different viewing angles.

[0043] In the actual implementation process, for each headlight, the headlight is controlled to project the feature calibration image, and the projection plane can be selected from the ground or the wall.

[0044] The feature calibration image is a pre-set image, which includes multiple preset feature points. The positions of the feature points in the image can be set according to the needs of actual applications. The number of multiple feature points is greater than the preset number, and the preset number can be set according to the needs of actual applications. For example, the preset number can be set to 4, that is, a feature calibration image includes at least 4 feature points. The more feature points there are, the more accurate the homography matrix obtained.

[0045] After the feature calibration image is projected onto the projection plane, a world coordinate system can be established in the projection plane. For example, the upper left corner of the projection image corresponding to the feature calibration image can be selected in the projection plane as the origin of the world coordinate system. In the actual implementation process, the origin of the world coordinate system can be selected according to needs, and this embodiment does not impose any restrictions.

[0046] After the world coordinate system is established on the projection plane, the projection coordinates of each feature point in the feature calibration image in the world coordinate system are determined according to the projection of each headlight on the feature calibration image.

[0047] During the calibration process, the projection coordinates of each feature point can be measured manually using a rangefinder or caliper and then uploaded, or other methods can be used to obtain the projection coordinates of each feature point in the world coordinate system. This embodiment does not impose any restrictions.

[0048] Then, the homography matrix corresponding to the vehicle light is calculated according to the projection coordinates of each feature point and the pixel coordinates of each feature point in the feature calibration image.

[0049] For example, when the projection plane is the ground, the homography matrix can be solved according to the homography projection equation:

[0050] in, H is a 3*3 homography matrix, ( u i , v i ,1) is the pixel coordinate of the feature point; ( X i , Y i , 1) is the projection coordinate of the feature point in the world coordinate system; since the projection plane is the ground, the Z-axis coordinate of each feature point can be regarded as 1.

[0051] A2: Determine, according to the homography matrices of the plurality of headlights, a binary mask image corresponding to the maximum projection area of ​​each of the plurality of headlights.

[0052] After determining the homography matrices of multiple headlights, the binary mask images corresponding to the maximum projection areas of each headlight can be determined based on the maximum projection areas corresponding to each headlight. In the binary mask image corresponding to the maximum projection area of ​​a headlight, the value of the pixel points in the maximum projection area of ​​the headlight is 1, and the value of the pixel points in the non-maximum projection area is 0.

[0053] Specifically, the sizes of the maximum projection images supported by the multiple headlights of the vehicle are the same, but after the multiple headlights project the maximum projection image, the maximum projection areas of different headlights on the projection plane are different.

[0054] Therefore, first, the maximum projection areas of the plurality of headlights are determined according to the maximum projection images of the plurality of headlights and the homography matrices of the plurality of headlights.

[0055] Specifically, for each headlight, the projection coordinates of each corner point of the maximum projection area corresponding to the headlight can be calculated based on the pixel coordinates of each corner point of the maximum projection image corresponding to the headlight and the homography matrix of the headlight. The projection coordinates are the coordinates of each corner point in the world coordinate system. Then, based on the projection coordinates of the four corner points of the headlight, the maximum projection area of ​​the headlight can be determined.

[0056] Through the feature calibration images and maximum projection images of multiple headlights, the maximum projection area of ​​each headlight can be uniformly aligned in the world coordinate system through geometric calibration.

[0057] Next, the minimum circumscribed rectangle corresponding to the maximum projection area of ​​each of the plurality of vehicle lights is determined.

[0058] Specifically, according to the projection coordinates of each corner point of the maximum projection area of ​​each of the multiple headlights, the four corner points corresponding to the maximum projection horizontal coordinate, the minimum projection horizontal coordinate, the maximum projection vertical coordinate and the minimum projection vertical coordinate are determined. According to the four corner points, the minimum enclosing rectangle corresponding to the maximum projection area of ​​each of the multiple headlights can be determined, and a binary mask image corresponding to the minimum enclosing rectangle is generated, and the values ​​of each pixel point of the binary mask image of the minimum enclosing rectangle are all 0.

[0059] Reference Figure 2 , shows a schematic diagram of the binary mask map of the minimum enclosing rectangle provided by an embodiment of the present application. Taking multiple headlights including a left headlight and a right headlight as an example, the dotted white box on the left side of the figure is the maximum projection area of ​​the left headlight, and the dotted white box on the right side is the maximum projection area of ​​the right headlight. The maximum projection areas of the two headlights each have a total of 8 corner points. According to the 4 corner points corresponding to the maximum projection horizontal coordinate, the minimum projection horizontal coordinate, the maximum projection vertical coordinate and the minimum projection vertical coordinate, the minimum enclosing rectangle of the maximum projection area of ​​the two headlights can be determined. After determining the size of the minimum enclosing rectangle, the binary mask map CA of the minimum enclosing rectangle can be generated, and the values ​​of each pixel point of the binary mask map of the minimum enclosing rectangle are set to 0.

[0060] Finally, according to the size of the minimum circumscribed rectangle and the maximum projection area of ​​each of the plurality of headlights, a binary mask image corresponding to each of the maximum projection areas of the plurality of headlights is determined.

[0061] Reference Figure 3, shows a schematic diagram of the binary mask image corresponding to the maximum projection area of ​​each headlight provided in this embodiment. Taking multiple headlights including left and right headlights as an example, the value of each pixel point in the binary mask image CA of the minimum circumscribed rectangle is 0, as shown in the black part, and the binary mask image CA of the minimum circumscribed rectangle can be copied twice.

[0062] In the first binary mask image CA of the minimum circumscribed rectangle, the values ​​within the range formed by the four corner points of the maximum projection area of ​​the left headlight are updated to 1, as shown in the white part, and the remaining values ​​remain 0. This can obtain the binary mask image CA1 corresponding to the maximum projection area of ​​the left headlight.

[0063] In the second binary mask image CA of the minimum circumscribed rectangle, the values ​​within the range formed by the four corner points of the right headlight's maximum projection area are updated to 1, as shown in white, and the remaining values ​​remain 0. This yields the binary mask image CA2 corresponding to the right headlight's maximum projection area.

[0064] A3: Determine a joint projection area of ​​the multiple headlights according to the binary mask images corresponding to the maximum projection areas of the respective headlights.

[0065] Specifically, the joint projection area refers to an area composed of the respective maximum projection areas of multiple headlights. For example, an OR operation can be performed on the binary mask images corresponding to the respective maximum projection areas of the multiple headlights to determine the joint projection area of ​​the multiple headlights.

[0066] Reference Figure 4 , shows a schematic diagram of the binary mask map of the joint projection area provided in an embodiment of the present application. Taking multiple headlights including a left headlight and a right headlight as an example, after the binary mask map CA1 corresponding to the maximum projection area of ​​the left headlight and the binary mask map CA2 corresponding to the maximum projection area of ​​the right headlight are ORed, the binary mask map of the joint projection area after the respective projection areas of the two headlights are combined can be determined, as shown in the white part in the figure.

[0067] When projecting any image within the joint projection area of ​​multiple headlights, the multiple headlights can project a complete image. However, in order to further correct the projected image and avoid distortion of the projected image, it is necessary to further determine the projection area when the multiple headlights jointly project within the joint projection area.

[0068] S102: Determine a target rectangular area in the joint projection area of ​​the plurality of headlights as the projection area when the plurality of headlights jointly project.

[0069] In order to make the projection area of ​​multiple headlights more square when projecting together, so as to improve the visual effect of the projection, this embodiment determines a rectangular projection area in the joint projection area of ​​the multiple headlights.

[0070] Specifically, the target rectangle is determined in the joint projection area of ​​the plurality of vehicle lights. The size of the target rectangle may be set according to actual application requirements, and is not limited in this embodiment.

[0071] For example, the target rectangle includes a maximum inscribed rectangle. In the joint projection area, the maximum inscribed rectangle can be determined through the maximum rectangle algorithm, and a binary mask image of the maximum inscribed rectangle can be generated, so that the area of ​​the projection area when multiple headlights are projected together is maximized, further improving the projection effect.

[0072] In actual implementation, any algorithm for determining the largest inscribed rectangle in an irregular shape may be used as the largest rectangle algorithm, and this embodiment does not impose any limitation.

[0073] Reference Figure 5 , shows a schematic diagram of the binary mask image of the maximum inscribed rectangle provided by an embodiment of the present application. Taking multiple headlights including left and right headlights as an example, the dotted white box on the left side of the figure is the maximum projection area of ​​the left headlight, and the dotted white box on the right side is the maximum projection area of ​​the right headlight. After determining the width and height of the maximum inscribed rectangle in the joint projection area, a binary mask image CA of the minimum circumscribed rectangle is copied, and the values ​​of the pixel points corresponding to the area of ​​the maximum inscribed rectangle are updated to 1. The binary mask image CA* of the maximum inscribed rectangle can be obtained, and the maximum inscribed rectangle is shown as the white part.

[0074] In the actual implementation process, after determining the area of ​​the maximum inscribed rectangle, the coordinates of any point in the area are marked. This point is used as the reference point when subsequently projecting any image to be projected. The value of the maximum inscribed rectangle is replaced by the pixel value of the image to be projected. For example, the upper left corner of the maximum inscribed rectangle can be selected as the reference point, and the coordinates of this point (x_mrt, y_mrt) can be recorded.

[0075] Specifically, after calibration, the homography matrices of multiple headlights, the maximum projection image and the binary mask map corresponding to the maximum projection area, as well as the binary mask map of the projection area of ​​multiple headlights can be stored as projection calibration data in a storage device on the vehicle. When any image needs to be projected, the stored projection calibration data can be directly obtained to process the image to be projected, so that multiple headlights can project the image to be projected into the projection area of ​​multiple headlights.

[0076] This method determines, through calibration, the area corresponding to a target rectangle in the joint projection area of ​​multiple headlights as the projection area when two headlights are jointly projected. The projection area is a rectangular area. The correction optimizes the shape of the projection area, avoids the problem of distortion of the final projection image when two headlights are jointly projected, and improves the projection effect of the headlights.

[0077] Reference Figure 6 , shows a flowchart of a vehicle light projection method in an embodiment of the present application, the method may specifically include the following steps: S201: When multiple headlights are projecting together, performing distortion correction on a projected image according to projection areas of the multiple headlights, where the projection area is a target rectangular area within the joint projection area of ​​the multiple headlights.

[0078] After pre-calibration, the projection area when multiple headlights are projected together has been determined. First, distortion correction can be performed on the projected image based on the projection area when multiple headlights are projected together.

[0079] Specifically, first, the image to be projected is scaled according to the size of the target rectangular area to obtain the distortion-corrected image to be projected.

[0080] The size of the target rectangle can be calibrated according to actual application requirements. For example, in order to maximize the area of ​​the projection area when multiple headlights are projected together, the target rectangle can include the largest inscribed rectangle in the joint projection area.

[0081] Taking the target rectangle as the maximum inscribed rectangle as an example, the image to be projected is scaled according to the width and height of the maximum inscribed rectangle to reduce the distortion of the image to be projected after projection so that the size of the scaled image to be projected is consistent with the size of the maximum inscribed rectangle.

[0082] Then, according to the reference point pre-marked in the maximum inscribed rectangle, the scaled image to be projected is used to cover the binary mask image of the maximum inscribed rectangle. For example, when the reference point selects the upper left corner point of the maximum inscribed rectangle, the upper left corner point of the scaled image to be projected is aligned with the upper left corner point of the binary mask image CA* of the maximum inscribed rectangle, and the pixel values ​​of the binary mask image CA* of the maximum inscribed rectangle are replaced with the pixel values ​​of the scaled image to be projected, so as to obtain the distortion-corrected image to be projected, so that the distortion-corrected image to be projected can completely cover the projection area without distortion, thereby improving the projection effect of the image.

[0083] Reference Figure 7 , a schematic diagram of the image to be projected after distortion correction provided by an embodiment of the present application is shown. Taking multiple headlights including left and right headlights as an example, the left box in the figure is the maximum projection area of ​​the left headlight, and the right box is the maximum projection area of ​​the right headlight. The pixel values ​​of the binary mask image CA* of the maximum inscribed rectangle are replaced with the pixel values ​​of the scaled image to be projected to obtain the binary mask image of the image to be projected after distortion correction. The binary mask image of the image to be projected after distortion correction can represent a black and white image or a grayscale image, which is not limited in this embodiment.

[0084] S202: Determine target images to be projected when each of the plurality of vehicle lights is projected, based on the distortion-corrected images to be projected.

[0085] Since there is a projection overlapping area when multiple car lights are projected together, in order to avoid the display difference between the image in the projection overlapping area and the image in the non-projection overlapping area when multiple car lights are projected together, such as the inconsistent display brightness of the images in the projection overlapping area and the non-projection overlapping area, a gradual fusion strategy can be further implemented to make the images in the projection overlapping area and the non-projection overlapping area transition smoothly, maintain consistent brightness, and further enhance the projection effect.

[0086] Specifically, the process of respectively determining the target images to be projected when the plurality of vehicle lights are projected according to the distortion-corrected images to be projected may include the following steps: B1: executing a gradient fusion strategy based on the overlapping projection areas of the multiple headlights and the distortion-corrected image to be projected, and determining gradient images of the multiple headlights respectively.

[0087] Specifically, an AND operation may be performed on the binary mask images corresponding to the respective maximum projection areas of the plurality of headlights to determine the binary mask images of the overlapping projection areas of the plurality of headlights.

[0088] After calibration, the maximum projection areas of multiple headlights are represented in a unified world coordinate system. By performing AND operations on the binary mask images corresponding to the maximum projection areas of multiple headlights, the overlapping areas of the projections of multiple headlights can be determined. This method is not restricted by the shape of the overlapping area, has higher adaptability, is convenient to calculate, and requires less computation.

[0089] The gradient fusion strategy is used to ensure that the projection brightness of the multiple vehicle lights in the projection overlap area and the non-projection overlap area remain consistent.

[0090] In a feasible implementation, executing the gradient fusion strategy to determine the gradient images of the plurality of headlights may include the following steps: B11: Determine coefficient matrices of overlapping images corresponding to each of the plurality of headlights according to the projection overlap areas of the plurality of headlights and the distortion-corrected image to be projected.

[0091] Specifically, after distortion correction, an AND operation is performed on the binary mask image of the distortion-corrected image to be projected and the binary mask image of the overlapping area of ​​the projections of the multiple headlights, so as to extract the overlapping images of the multiple headlights.

[0092] Then, for the overlapping images of each headlight, the linear coefficient after gamma correction corresponding to each pixel point is determined row by row to obtain a coefficient matrix of the overlapping image corresponding to the headlight.

[0093] Taking multiple headlights including left and right headlights as an example, for each row of pixels in the overlapping image of the left headlight, the first linear coefficients corresponding to each pixel are determined in descending order from left to right, and the first linear coefficients are gamma corrected to determine the first coefficient matrix w_left of the overlapping image of the left headlight.

[0094] For example, for the overlapping image of the left headlight, the first linear coefficients of the pixels in different rows of the same column are the same, and the first linear coefficients corresponding to the pixels in different columns of the same row are determined in descending order from left to right according to the preset linear coefficient difference. Therefore, in the projected image display, the overlapping image of the left headlight has an effect of gradually decreasing brightness from left to right.

[0095] Then, for the overlapping image of the right headlight, the second linear coefficient of each pixel point in the overlapping image of the left headlight is determined based on the first linear coefficient corresponding to each pixel point in the overlapping image of the right headlight, and the second linear coefficient is gamma corrected to determine the second coefficient matrix w_righ of the overlapping image of the right headlight.

[0096] After the first linear coefficient of any pixel point in the overlapping image of the left headlight is determined, the difference between 1 and the first linear coefficient of the pixel point can be used as the second linear coefficient of the pixel point in the overlapping image of the right headlight. As a result, in the projected image display, the overlapping image of the right headlight has an effect of gradually decreasing brightness from right to left, and after the left and right headlights overlap, the display brightness of the overlapping image can be smoothly filtered to ensure smooth fusion and lighting consistency when the projected images are displayed in the overlapping area of ​​the two headlights.

[0097] In actual implementation, when performing gamma correction on any linear coefficient, γ may be 1.8, or a corresponding γ value may be selected according to actual application requirements, which is not limited in this embodiment.

[0098] B12: Determine the gradient images of the plurality of headlights according to the coefficient matrix of the distortion-corrected image to be projected and the overlapping images corresponding to the plurality of headlights.

[0099] In actual implementation, two binary mask images of the distortion-corrected image to be projected may be copied.

[0100] Multiply a binary mask of the distortion-corrected image to be projected by the first coefficient matrix w_left of the left headlight to obtain a gradient image corresponding to the left headlight. Another binary mask image of the distortion-corrected image to be projected is multiplied by the second coefficient matrix w_right of the right headlight to obtain a gradient image corresponding to the right headlight.

[0101] Reference Figure 8 , shows a visualization schematic diagram of the gradient images of each headlight provided in an embodiment of the present application, wherein the brightness of the non-overlapping images of the left headlight is consistent, and the overlapping images have an effect of gradually decreasing brightness from left to right; the brightness of the non-overlapping images of the right headlight is consistent, and the overlapping images have an effect of gradually decreasing brightness from right to left.

[0102] By executing the gradient fusion strategy and determining the gradient images of multiple headlights, the brightness of the image in the overlapping projection area and the image in the non-overlapping projection area can be kept consistent when multiple headlights are projected together, thereby improving the image projection effect.

[0103] B2: Determine target images to be projected by each of the plurality of headlights according to the respective gradient images of the plurality of headlights.

[0104] Since the obtained gradient images of the multiple headlights are all images corresponding to the projection plane, a perspective transformation is required to convert the images of the projection plane into the target images to be projected that the two headlights actually need to project.

[0105] Specifically, according to the homography matrices and the maximum projection image corresponding to the multiple headlights, perspective transformation is performed on the gradient images corresponding to the multiple headlights to determine the target images to be projected by the multiple headlights.

[0106] Reference Figure 9 , shows a schematic diagram of the target images to be projected of each headlight provided in an embodiment of the present application. After the gradient images of the left headlight and the right headlight are perspective transformed, the target images to be projected of the left headlight and the right headlight can be determined.

[0107] After determining the target images to be projected by multiple headlights, the multiple headlights can be controlled to project their respective target images, and then the projection images after distortion correction and brightness fusion can be displayed on the projection plane. The projection images in the projection plane can be fully displayed in the projection area.

[0108] The car light projection area calibration method and car light projection method provided in this embodiment can ensure that when multiple car lights are projected together, the shape of the final projection image is a square rectangle, avoiding distortion of the projection image, and the display brightness of the projection image is uniform, thereby enhancing the projection effect when multiple car lights are projected together.

[0109] Reference Figure 10 , shows a structural schematic diagram of a projection control system provided in an embodiment of the present application, wherein the system includes multiple vehicle lights, a control module, a controller, and a motor assembly.

[0110] For example, the plurality of vehicle lamps may include a left DLP lamp and a right DLP lamp.

[0111] The output end of the control module is connected to the input end of the controller, and the output end of the controller is respectively connected to the motor assembly, the left DLP lamp and the right DLP lamp, and the left DLP lamp and the right DLP lamp are used to project any image.

[0112] The control module is used to send CAN instructions to the controller. The control module is used to execute the headlight projection area calibration method described in this embodiment, or execute the headlight projection method described. For example, the control module can use the TDA4VE chip and use the computing power of the integrated graphics card in the chip to calculate the fusion of the dual DLP lamp projection area and the projection transformation process, thereby improving the efficiency of projection image processing.

[0113] The controller is used to control the motor assembly to adjust the projection angle or projection plane of the two DLP lamps after receiving CAN commands from the control module. The projection angle can be divided into three levels: wall projection, distance projection, and ground projection.

[0114] The present application also provides a vehicle lamp projection device, the projection device comprising: a distortion correction module, configured to perform distortion correction on a projected image when multiple headlights are projecting together, based on a projection area of ​​the multiple headlights, where the projection area is a target rectangular area within the joint projection area of ​​the multiple headlights; The target projection image determination module is used to determine the target images to be projected when each of the multiple headlights is projected according to the distortion-corrected images to be projected.

[0115] Optionally, the target rectangle includes a maximum inscribed rectangle.

[0116] Optionally, the distortion correction module is used to: The image to be projected is scaled according to the size of the target rectangular area to obtain the distortion-corrected image to be projected.

[0117] Optionally, the target projection image determination module includes: a gradient processing unit, configured to execute a gradient fusion strategy based on the overlapping projection areas of the plurality of headlights and the distortion-corrected image to be projected, and to determine gradient images of the plurality of headlights respectively; The target projection image determination unit is used to determine the target images to be projected by each of the multiple headlights according to the gradient images of each of the multiple headlights.

[0118] Optionally, an AND operation is performed on binary mask images corresponding to the maximum projection areas of the multiple headlights to determine an overlapping area of ​​the projections of the multiple headlights.

[0119] Optionally, the gradient processing unit includes: a coefficient matrix determining unit, configured to determine coefficient matrices of overlapping images corresponding to the plurality of headlights, respectively, based on the overlapping areas of the projections of the plurality of headlights and the distortion-corrected image to be projected; The gradient image determining unit is configured to determine the gradient images of the plurality of headlights according to the coefficient matrix of the distortion-corrected image to be projected and the overlapping images corresponding to the plurality of headlights.

[0120] Optionally, an AND operation is performed on the binary mask image corresponding to the overlapping area of ​​the projections of the multiple headlights and the image to be projected after distortion correction to determine the overlapping images corresponding to the multiple headlights.

[0121] Optionally, the coefficient matrix determination unit is used to: For the overlapping images of each headlight, the linear coefficient after gamma correction corresponding to each pixel point is determined row by row to obtain a coefficient matrix of the overlapping image corresponding to the headlight.

[0122] Optionally, the plurality of headlights include a left headlight and a right headlight, and the coefficient matrix determination unit is configured to: For each row of pixels in the overlapping image of the left headlight, determining first linear coefficients corresponding to the pixels in descending order from left to right, and performing gamma correction on the first linear coefficients to determine a first coefficient matrix for the overlapping image of the left headlight; For the overlapping image of the right headlight, the second linear coefficient of each pixel point in the overlapping image of the left headlight is determined based on the first linear coefficient corresponding to each pixel point in the overlapping image of the right headlight, and the second linear coefficient is gamma corrected to determine the second coefficient matrix of the overlapping image of the right headlight.

[0123] Optionally, the target projection image determination unit is configured to: According to the homography matrices and the maximum projection image corresponding to the multiple headlights, perspective transformation is performed on the gradient images corresponding to the multiple headlights to determine target images to be projected by the multiple headlights.

[0124] The present application also provides a device for calibrating a vehicle lamp projection area, the device comprising: a joint projection area determination module, configured to determine the joint projection area of ​​the plurality of headlights when the projections of the plurality of headlights overlap; The projection area determination module is used to determine a target rectangular area in the joint projection area of ​​the multiple headlights as the projection area when the multiple headlights are jointly projected.

[0125] Optionally, the target rectangle includes a maximum inscribed rectangle.

[0126] Optionally, the projection area determination module is used to: In the joint projection area of ​​the multiple vehicle lights, the area of ​​the maximum inscribed rectangle is determined by a maximum rectangle algorithm.

[0127] Optionally, the joint projection area determination module includes: The joint projection area determining unit is configured to determine the joint projection area of ​​the plurality of headlights according to the binary mask images corresponding to the respective maximum projection areas of the plurality of headlights.

[0128] Optionally, the joint projection area determining unit is configured to: An OR operation is performed on the binary mask images corresponding to the respective maximum projection areas of the plurality of headlights to determine a joint projection area of ​​the plurality of headlights.

[0129] Optionally, the calibration device further includes: The maximum projection area determination module is used to determine the binary mask images corresponding to the maximum projection areas of the plurality of headlights according to the homography matrices of the plurality of headlights.

[0130] Optionally, the calibration device further includes: a homography matrix calculation module, configured to determine, for each headlight, the projection coordinates of each feature point in the feature calibration image based on the projection of the headlight onto the feature calibration image; The homography matrix corresponding to the vehicle light is calculated according to the projection coordinates of each feature point and the pixel coordinates of each feature point in the feature calibration image.

[0131] Optionally, the feature calibration image includes a plurality of feature points, and the number of the plurality of feature points is greater than a preset number.

[0132] Optionally, the maximum projection area determination module includes: a maximum projection area determining unit, configured to determine the maximum projection area of ​​each of the plurality of headlights according to the maximum projection images of each of the plurality of headlights and the homography matrices of each of the plurality of headlights; a minimum circumscribed rectangle determining unit, configured to determine a minimum circumscribed rectangle corresponding to the maximum projection area of ​​each of the plurality of headlights; The binary mask image determining unit is configured to determine the binary mask images corresponding to the maximum projection areas of the plurality of headlights according to the size of the minimum circumscribed rectangle and the maximum projection areas of the plurality of headlights.

[0133] Optionally, the maximum projection area determining unit is further configured to: For each headlight, the projection coordinates of each corner point of the maximum projection area corresponding to the headlight are calculated based on the pixel coordinates of each corner point of the maximum projection image corresponding to the headlight and the homography matrix of the headlight to determine the maximum projection area of ​​the headlight.

[0134] Optionally, the minimum bounding rectangle determining unit is further configured to: Determine, according to the projection coordinates of the corner points of the maximum projection areas of the plurality of headlights, four corner points corresponding to the maximum projection abscissa, the minimum projection abscissa, the maximum projection ordinate, and the minimum projection ordinate; Determine, based on the four corner points, a minimum circumscribed rectangle corresponding to the maximum projection area of ​​each of the plurality of headlights.

[0135] Reference Figure 11 , shows a schematic diagram of an electronic device provided in an embodiment of the present application, comprising: at least one processor, and a memory, wherein the memory stores a computer program that can be run on the processor, wherein when the processor executes the computer program, it executes the vehicle light projection area calibration method described in this embodiment, or executes the vehicle light projection method described in this embodiment.

[0136] Reference Figure 12 , shows a schematic diagram of a non-volatile readable storage medium provided in an embodiment of the present application, wherein the non-volatile readable storage medium stores a computer program, wherein when the computer program is executed by a processor, the method for calibrating the vehicle light projection area described in this embodiment is executed, or the vehicle light projection method described in this embodiment is executed.

[0137] Reference Figure 13 , shows a schematic diagram of a computer program product provided in an embodiment of the present application, including a computer program / instruction, which, when executed by a processor, implements the vehicle light projection area calibration method described in this embodiment, or executes the vehicle light projection method described in this embodiment.

[0138] An embodiment of the present application also provides a vehicle, which is provided with the projection control system described in this embodiment, or is used to execute the vehicle light projection area calibration method described in this embodiment, or is used to execute the vehicle light projection method described in this embodiment.

[0139] The various embodiments in this specification are described in a progressive manner, and each embodiment focuses on the differences from other embodiments. The same or similar parts between the various embodiments can be referenced to each other.

[0140] Those skilled in the art will appreciate that the embodiments of the present application can be provided as methods, apparatuses, or computer program products. Therefore, the embodiments of the present application can take the form of entirely hardware embodiments, entirely software embodiments, or embodiments combining software and hardware. Furthermore, the embodiments of the present application can take the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to magnetic disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0141] The embodiments of the present application are described with reference to the flowcharts and / or block diagrams of the methods, terminal devices (systems) and computer program products according to the embodiments of the present application. It should be understood that each process and / or box in the flowchart and / or block diagram, as well as the combination of the processes and / or boxes in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor or other programmable data processing terminal device to produce a machine, so that the instructions executed by the processor of the computer or other programmable data processing terminal device generate instructions for implementing the steps in the process. Figure 1 a process or multiple processes and / or boxes Figure 1 A device that provides the functions specified in a block or multiple blocks.

[0142] These computer program instructions may also be stored in a computer readable memory that can direct a computer or other programmable data processing terminal device to operate in a specific manner, so that the instructions stored in the computer readable memory produce a manufactured product including an instruction device, which implements the process Figure 1 a process or multiple processes and / or boxes Figure 1 The function specified in one or more boxes.

[0143] These computer program instructions can also be loaded onto a computer or other programmable data processing terminal device so that a series of operating steps are executed on the computer or other programmable terminal device to produce a computer-implemented process, thereby providing instructions for executing on the computer or other programmable terminal device to implement the process. Figure 1 a process or multiple processes and / or boxes Figure 1 A step that specifies a function in one or more boxes.

[0144] Although preferred embodiments of the present invention have been described, those skilled in the art may make additional changes and modifications to these embodiments once they become aware of the basic inventive concepts. Therefore, the appended claims are intended to be interpreted as including the preferred embodiments and all changes and modifications that fall within the scope of the embodiments of the present invention.

[0145] Finally, it should be noted that, in this document, relational terms such as first and second, etc., are used only to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any actual relationship or order between these entities or operations. Moreover, the terms "comprises," "includes," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, method, article, or terminal device that includes a series of elements includes not only those elements, but also other elements not explicitly listed, or elements inherent to such process, method, article, or terminal device. In the absence of further limitations, an element defined by the phrase "comprises a..." does not exclude the presence of additional identical elements in the process, method, article, or terminal device that includes the element.

[0146] This document uses specific examples to illustrate the principles and implementation methods of this application. The description of the above embodiments is only used to help understand the method and core ideas of this application. At the same time, for those skilled in the art, based on the ideas of this application, there will be changes in the specific implementation methods and application scope. In summary, the content of this specification should not be understood as limiting this application.

Claims

1. A vehicle light projection method, characterized in that: The method comprises: When multiple headlights are projected together, distortion correction is performed on the projected image according to the projection areas of the multiple headlights, where the projection area is the target rectangular area within the joint projection area of ​​the multiple headlights; According to the distortion-corrected image to be projected, target images to be projected when each of the plurality of vehicle lights is projected are determined respectively.

2. The method according to claim 1, characterized in that The target rectangle includes a maximum inscribed rectangle.

3. The method according to claim 1, characterized in that Performing distortion correction on the projected image according to the projection areas of the multiple vehicle lights, including: The image to be projected is scaled according to the size of the target rectangular area to obtain the distortion-corrected image to be projected.

4. The method according to any one of claims 1 to 3, characterized in that Determining target images to be projected when each of the plurality of vehicle lights is projected according to the distortion-corrected image to be projected, including: executing a gradient fusion strategy according to the overlapping projection areas of the plurality of headlights and the distortion-corrected image to be projected, and determining gradient images of the plurality of headlights respectively; According to the respective gradient images of the plurality of headlights, target images to be projected by the respective headlights are determined.

5. The method according to claim 4, characterized in that The method further comprises: An AND operation is performed on the binary mask images corresponding to the maximum projection areas of the multiple headlights to determine an overlapping area of ​​the projections of the multiple headlights.

6. The method according to claim 4, characterized in that Executing a gradient fusion strategy based on the overlapping projection areas of the plurality of headlights and the distortion-corrected image to be projected to determine gradient images of the plurality of headlights respectively includes: Determining coefficient matrices of overlapping images corresponding to the plurality of headlights, respectively, based on the projection overlap areas of the plurality of headlights and the distortion-corrected image to be projected; The gradient images of the plurality of headlights are determined according to the coefficient matrices of the distortion-corrected image to be projected and the overlapping images corresponding to the plurality of headlights.

7. The method according to claim 6, characterized in that The method further comprises: An AND operation is performed on the binary mask image corresponding to the overlapping area of ​​the projections of the multiple headlights and the image to be projected after the distortion correction to determine the overlapping images corresponding to the multiple headlights.

8. The method according to claim 6, characterized in that Determining coefficient matrices of overlapping images corresponding to each of the plurality of vehicle lights, respectively, includes: For the overlapping images of each headlight, the linear coefficient after gamma correction corresponding to each pixel point is determined row by row to obtain a coefficient matrix of the overlapping image corresponding to the headlight.

9. The method according to claim 8, characterized in that The plurality of headlights include a left headlight and a right headlight. For overlapping images of the respective headlights, a linear coefficient corresponding to each pixel after gamma correction is determined row by row to obtain a coefficient matrix of the overlapping images corresponding to the respective headlights, including: For each row of pixels in the overlapping image of the left headlight, determining first linear coefficients corresponding to the pixels in descending order from left to right, and performing gamma correction on the first linear coefficients to determine a first coefficient matrix for the overlapping image of the left headlight; For the overlapping image of the right headlight, the second linear coefficient of each pixel point in the overlapping image of the left headlight is determined based on the first linear coefficient corresponding to each pixel point in the overlapping image of the right headlight, and the second linear coefficient is gamma corrected to determine the second coefficient matrix of the overlapping image of the right headlight.

10. The method according to any one of claims 5 to 9, characterized in that: Determining target images to be projected by each of the plurality of headlights according to the respective gradient images of the plurality of headlights includes: According to the homography matrices and the maximum projection image corresponding to the multiple headlights, perspective transformation is performed on the gradient images corresponding to the multiple headlights to determine target images to be projected by the multiple headlights.

11. A method for calibrating a vehicle lamp projection area, characterized in that: The method comprises: When projections of multiple headlights overlap, determining a joint projection area of ​​the multiple headlights; A target rectangular area is determined in the joint projection area of ​​the multiple headlights as the projection area when the multiple headlights are jointly projected.

12. The method according to claim 11, characterized in that The target rectangle includes a maximum inscribed rectangle.

13. The method according to claim 12, characterized in that Determining a target rectangular area in a joint projection area of ​​the plurality of vehicle lights includes: In the joint projection area of ​​the multiple vehicle lights, the area of ​​the maximum inscribed rectangle is determined by a maximum rectangle algorithm.

14. The method according to any one of claims 11 to 13, characterized in that: Determining a joint projection area of ​​the plurality of vehicle lights includes: The joint projection area of ​​the multiple headlights is determined according to the binary mask images corresponding to the maximum projection areas of the respective headlights.

15. The method according to claim 14, characterized in that Determining a joint projection area of ​​the plurality of headlights according to the binary mask images corresponding to the respective maximum projection areas of the plurality of headlights includes: An OR operation is performed on the binary mask images corresponding to the respective maximum projection areas of the plurality of headlights to determine a joint projection area of ​​the plurality of headlights.

16. The method according to claim 14, characterized in that The method further comprises: According to the homography matrices of the plurality of headlights, binary mask images corresponding to the maximum projection areas of the plurality of headlights are determined.

17. The method according to claim 16, characterized in that The method further comprises: For each headlight, determining the projection coordinates of each feature point in the feature calibration image based on the projection of the headlight on the feature calibration image; The homography matrix corresponding to the vehicle light is calculated according to the projection coordinates of each feature point and the pixel coordinates of each feature point in the feature calibration image.

18. The method according to claim 17, characterized in that The feature calibration image includes a plurality of feature points, and the number of the plurality of feature points is greater than a preset number.

19. The method according to any one of claims 16 to 18, characterized in that: Determining, according to the homography matrices of the plurality of headlights, binary mask images corresponding to the maximum projection areas of the plurality of headlights, includes: determining the maximum projection areas of the plurality of headlights according to the maximum projection images of the plurality of headlights and the homography matrices of the plurality of headlights; Determining a minimum circumscribed rectangle corresponding to the maximum projection area of ​​each of the plurality of headlights; According to the size of the minimum circumscribed rectangle and the maximum projection area of ​​each of the plurality of headlights, a binary mask image corresponding to the maximum projection area of ​​each of the plurality of headlights is determined respectively.

20. The method according to claim 19, characterized in that Determining the maximum projection areas of the plurality of headlights according to the maximum projection images of the plurality of headlights and the homography matrices of the plurality of headlights includes: For each headlight, the projection coordinates of each corner point of the maximum projection area corresponding to the headlight are calculated based on the pixel coordinates of each corner point of the maximum projection image corresponding to the headlight and the homography matrix of the headlight to determine the maximum projection area of ​​the headlight.

21. The method according to claim 19, wherein Determining the minimum circumscribed rectangle corresponding to the maximum projection area of ​​each of the plurality of headlights includes: Determine, according to the projection coordinates of the corner points of the maximum projection areas of the plurality of headlights, four corner points corresponding to the maximum projection abscissa, the minimum projection abscissa, the maximum projection ordinate, and the minimum projection ordinate; Determine, based on the four corner points, a minimum circumscribed rectangle corresponding to the maximum projection area of ​​each of the plurality of headlights.

22. A projection control system, characterized in that: The system includes multiple vehicle lights and a control module, and the control module is used to execute the vehicle light projection method described in any one of claims 1-10, or execute the vehicle light projection area calibration method described in any one of claims 11-21.

23. An electronic device, characterized in that: include: At least one processor, and a memory storing a computer program that can be run on the processor, wherein when the processor executes the computer program, it executes the vehicle light projection method described in any one of claims 1-10, or executes the vehicle light projection area calibration method described in any one of claims 11-21.

24. A non-volatile readable storage medium, characterized in that The non-volatile readable storage medium stores a computer program, wherein when the computer program is executed by a processor, the vehicle light projection method according to any one of claims 1 to 10 is executed, or the vehicle light projection area calibration method according to any one of claims 11 to 21 is executed.

25. A computer program product comprising a computer program / instructions, characterized in that When the computer program / instruction is executed by a processor, the vehicle light projection method according to any one of claims 1 to 10 is implemented, or the vehicle light projection area calibration method according to any one of claims 11 to 21 is implemented.

26. A vehicle, characterized in that: The vehicle is used to execute the vehicle light projection method described in any one of claims 1-10, or execute the vehicle light projection area calibration method described in any one of claims 11-21, or includes the projection control system described in claim 21.

Images